Home โ€บ Tools โ€บ LLM Provider / Model โ€บ Qwen 3.5 397B-A17B

Qwen 3.5 397B-A17B

LLM Provider / Model ยท Frontier open-weight reasoning, native multimodal tasks (text/image/video co-trained), commercial use under Apache 2.0, Alibaba Cloud Model Studio (1M ctx hosted)

At a glance

Input priceFree (self-hosted)
Output priceFree (self-hosted)
Price tierFree
Context window256K
Max output32K
Context tier128K-500K
Speed tierStandard
Latencylocal-bound
Knowledge cutoffDec 2025
ModalityMultimodal (vision)
Model IDqwen3.5-397b-a17b
ProviderAlibaba
HumanEval91%
MMLU87%
SWE-Bench71%
BenchmarkGDPval-AA: top open
ReleasedFeb 2026
HostingOpen-weights
CapabilitiesVision, Tool use, Streaming, Structured output, MoE (397B / 17B active, 512 experts), Native multimodal training, Function calling, Apache 2.0, Self-hostable

What Qwen 3.5 397B-A17B does

Vision, Tool use, Streaming, Structured output, MoE (397B / 17B active, 512 experts), Native multimodal training, Function calling, Apache 2.0, Self-hostable

Best for

Frontier open-weight reasoning, native multimodal tasks (text/image/video co-trained), commercial use under Apache 2.0, Alibaba Cloud Model Studio (1M ctx hosted)

Works well with

Conflicts & caveats

Build a full stack around Qwen 3.5 397B-A17B โ€” Flowpicker shows compatibility warnings before you commit.

Open the stack planner โ†’